dequant_nvfp4_to_bf16

metrale_model_layers::weight_map::fp8_lut

Function dequant_nvfp4_to_bf16 

Source 
pub fn dequant_nvfp4_to_bf16(
    store: &WeightStore,
    prefix: &str,
    n: usize,
    k: usize,
    gpu: &dyn GpuBackend,
) -> Result<DenseWeight>
Expand description

2026-09-25: Dequantize an NVFP4 weight to a new BF16 GPU buffer, on the GPU.

Detects the layout from the store keys:

  • compressed-tensors: weight_packed, weight_scale, weight_global_scale (reciprocal)
  • Standard (modelopt): weight, weight_scale, weight_scale_2 (direct multiplier)